Human-website interaction monitoring in recommender systems

The increasing amount of marketing content in e-commerce websites results in the limited attention of users. For recommender systems, the way recommended items are presented becomes as important as the underlying algorithms for product selection. In order to improve the effectiveness of content presentation, marketing experts experiment with the layout and other visual aspects of website elements to find the most suitable solution. This study investigates those aspects for a recommending interface. We propose a framework for performance evaluation of a recommending interface, which takes into consideration individual user characteristics and goals. At the heart of the proposed solution is a deep neutral network trained to predict the efficiency a particular recommendation presented in a selected position and with a chosen degree of intensity. The proposed Performance Evaluation of a Recommending Interface (PERI) framework can be used to automate an optimal recommending interface adjustment according to the characteristics of the user and their goals. The experimental results from the study are based on research-grade measurement electronics equipment Gazepoint GP3 eye-tracker data, together with synthetic data that were used to perform pre-assessment training of the neural network.

show abstract

“…[3]. Online systems process a wide stream of user data [4][5][6][7] essential to build user profiles and recommend…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Enhanced Framework for Performance Evaluation of a Recommending Interface with Varied Recommendation Position and Intensity Based on Eye-Tracking Equipment Data Processing

Sulikowski

Zdziebko

2020

Electronics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our e-commerce customer preference monitor (ECPM) was built in order to collect e-customer behavior data [ 2 ]. This monitoring tool was implemented as an extension for the Mozilla Firefox browser, with the core monitoring code being easily detachable and available for external use.…”

Section: Methodsmentioning

confidence: 99%

“…A digital representation of this model is a user profile, which usually reflects the user’s preferences and needs. Online websites can collect a broad spectrum of data [ 2 , 3 , 4 , 5 ] concerning users’ demographics and behavior, which are used to construct user profiles and generate personalized recommendations aimed to generate sales.…”

Section: Introductionmentioning

confidence: 99%

“…The most appropriate ways of presenting a recommendation item to users can be learned by observing human–computer interaction, with websites and recommending interfaces in particular. While interacting with websites, human behavior can be observed via eye tracking [ 13 ] or by collecting events inside modern web browsers [ 2 ], based respectively on gaze sensors and mouse/keystroke sensors. The investigation of visual aspects of recommending interfaces could better integrate those interfaces in online stores [ 10 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Gaze and Event Tracking for Evaluation of Recommendation-Driven Purchase

Sulikowski

Zdziebko

Coussement

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Recommendation systems play an important role in e-commerce turnover by presenting personalized recommendations. Due to the vast amount of marketing content online, users are less susceptible to these suggestions. In addition to the accuracy of a recommendation, its presentation, layout, and other visual aspects can improve its effectiveness. This study evaluates the visual aspects of recommender interfaces. Vertical and horizontal recommendation layouts are tested, along with different visual intensity levels of item presentation, and conclusions obtained with a number of popular machine learning methods are discussed. Results from the implicit feedback study of the effectiveness of recommending interfaces for four major e-commerce websites are presented. Two different methods of observing user behavior were used, i.e., eye-tracking and document object model (DOM) implicit event tracking in the browser, which allowed collecting a large amount of data related to user activity and physical parameters of recommending interfaces. Results have been analyzed in order to compare the reliability and applicability of both methods. Observations made with eye tracking and event tracking led to similar results regarding recommendation interface evaluation. In general, vertical interfaces showed higher effectiveness compared to horizontal ones, with the first and second positions working best, and the worse performance of horizontal interfaces probably being connected with banner blindness. Neural networks provided the best modeling results of the recommendation-driven purchase (RDP) phenomenon.

show abstract

“…The function scrolls down around half the display height, pauses for some time, scrolls further, pauses again and repeats this procedure until reaching the bottom of the page. We developed this function since scrolling is considered a typical behavior for human users on websites [42,36]. (ii) A function which allows switching between browser tabs.…”

Section: Humanoid Online Services Inspection Toolmentioning

confidence: 99%

Even Turing Should Sometimes Not Be Able to Tell: Mimicking Humanoid Usage Behavior for Exploratory Studies of Online Services

Wiefling

Gruschka

Iacono

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Online services such as social networks, online shops, and search engines deliver different content to users depending on their location, browsing history, or client device. Since these services have a major influence on opinion forming, understanding their behavior from a social science perspective is of greatest importance. In addition, technical aspects of services such as security or privacy are becoming more and more relevant for users, providers, and researchers. Due to the lack of essential data sets, automatic black box testing of online services is currently the only way for researchers to investigate these services in a methodical and reproducible manner. However, automatic black box testing of online services is difficult since many of them try to detect and block automated requests to prevent bots from accessing them. In this paper, we introduce a testing tool that allows researchers to create and automatically run experiments for exploratory studies of online services. The testing tool performs programmed user interactions in such a manner that it can hardly be distinguished from a human user. To evaluate our tool, we conducted-among other things-a large-scale research study on Risk-based Authentication (RBA), which required human-like behavior from the client. We were able to circumvent the bot detection of the investigated online services with the experiments. As this demonstrates the potential of the presented testing tool, it remains to the responsibility of its users to balance the conflicting interests between researchers and service providers as well as to check whether their research programs remain undetected.

show abstract

Human-website interaction monitoring in recommender systems

Cited by 24 publications

References 24 publications

Deep Learning-Enhanced Framework for Performance Evaluation of a Recommending Interface with Varied Recommendation Position and Intensity Based on Eye-Tracking Equipment Data Processing

Deep Learning-Enhanced Framework for Performance Evaluation of a Recommending Interface with Varied Recommendation Position and Intensity Based on Eye-Tracking Equipment Data Processing

Gaze and Event Tracking for Evaluation of Recommendation-Driven Purchase

Even Turing Should Sometimes Not Be Able to Tell: Mimicking Humanoid Usage Behavior for Exploratory Studies of Online Services

Contact Info

Product

Resources

About